---
library_name: mlx
model_name: QVikhr-3-4B-Instruction
base_model: Vikhrmodels/QVikhr-3-4B-Instruction
language:
- ru
- en
license: apache-2.0
datasets:
- Vikhrmodels/GrandMaster2
tags:
- mlx
pipeline_tag: text-generation
---

# Vikhrmodels/QVikhr-3-4B-Instruction-MLX_4bit

This model [Vikhrmodels/QVikhr-3-4B-Instruction-MLX_4bit](https://huggingface.co/Vikhrmodels/QVikhr-3-4B-Instruction-MLX_4bit) was
converted to MLX format from [Vikhrmodels/QVikhr-3-4B-Instruction](https://huggingface.co/Vikhrmodels/QVikhr-3-4B-Instruction)
using mlx-lm version **0.25.2**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("Vikhrmodels/QVikhr-3-4B-Instruction-MLX_4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```